Point Cloud Oversegmentation with Graph-Structured Deep Metric Learning
We propose a new supervized learning framework for oversegmenting 3D point clouds into superpoints. We cast this problem as learning deep embeddings of the local geometry and radiometry of 3D points, such that the border of objects presents high contrasts. The embeddings are computed using a lightweight neural network operating on the points' local neighborhood. Finally, we formulate point cloud oversegmentation as a graph partition problem with respect to the learned embeddings. This new approach allows us to set a new state-of-the-art in point cloud oversegmentation by a significant margin, on a dense indoor dataset (S3DIS) and a sparse outdoor one (vKITTI). Our best solution requires over five times fewer superpoints to reach similar performance than previously published methods on S3DIS. Furthermore, we show that our framework can be used to improve superpoint-based semantic segmentation algorithms, setting a new state-of-the-art for this task as well.
Code (2)
Tasks
Semantic SegmentationSimilar Papers 제목 키워드 기반
Supervized Segmentation with Graph-Structured Deep Metric Learning
We present a fully-supervized method for learning to segment data structured by an adjacency graph. We introduce the graph-structured contrastive loss, a loss function structured by a ground truth segmentation. It promot…
Metric LearningSegmentationEfficient LiDAR Point Cloud Oversegmentation Network
Point cloud oversegmentation is a challenging task since it needs to produce perceptually meaningful partitions (i.e., superpoints) of a point cloud. Most existing oversegmentation methods cannot efficiently generate…
LIDAR Semantic SegmentationSemantic SegmentationSuperpoint Network for Point Cloud Oversegmentation
Superpoints are formed by grouping similar points with local geometric structures, which can effectively reduce the number of primitives of point clouds for subsequent point cloud processing. Existing superpoint meth…
ClusteringSemantic SegmentationRecognising geometric primitives in 3D point clouds of mechanical CAD objects
The problem faced in this paper concerns the recognition of simple and complex geometric primitives in point clouds resulting from scans of mechanical CAD objects. A large number of points, the presence of noise, outlier…
3D Point Cloud Generative Adversarial Network Based on Tree Structured Graph Convolutions
In this paper, we propose a novel generative adversarial network (GAN) for 3D point clouds generation, which is called tree-GAN. To achieve state-of-the-art performance for multi-class 3D point cloud generation, a tree-s…
Generative Adversarial NetworkPoint Cloud Generation